Convergence of Batch Greenkhorn for Regularized Multimarginal Optimal Transport

In this work we propose a batch version of the Greenkhorn algorithm for multimarginal regularized optimal transport problems. Our framework is general enough to cover, as particular cases, some existing algorithms like Sinkhorn and Greenkhorn algorithm for the bi-marginal setting, and (greedy) MultiSinkhorn for multimarginal optimal transport. We provide a complete convergence analysis, which is based on the properties of the iterative Bregman projections (IBP) method with greedy control. Global linear rate of convergence and explicit bound on the iteration complexity are obtained. When specialized to above mentioned algorithms, our results give new insights and/or improve existing ones.

[1]  César A. Uribe,et al.  Multimarginal Optimal Transport by Accelerated Gradient Descent , 2020 .

[2]  Saverio Salzo,et al.  The method of Bregman projections in deterministic and stochastic convex feasibility problems , 2021, 2101.01704.

[3]  L. Bregman.  The relaxation method of finding the common point of convex sets and its application to the solution of problems in convex programming , 1967 .

[4]  Michael I. Jordan,et al.  On the Complexity of Approximating Multimarginal Optimal Transport , 2019, ArXiv.

[5]  Guillaume Carlier,et al.  Barycenters in the Wasserstein Space , 2011, SIAM J. Math. Anal..

[6]  Enric Boix-Adsera,et al.  Hardness results for Multimarginal Optimal Transport problems , 2020, Discret. Optim..

[7]  Nicolas Papadakis,et al.  Regularized Optimal Transport and the Rot Mover's Distance , 2016, J. Mach. Learn. Res..

[8]  Marco Cuturi,et al.  Computational Optimal Transport: With Applications to Data Science , 2019 .

[9]  Michael I. Jordan,et al.  On the Efficiency of Sinkhorn and Greenkhorn and Their Acceleration for Optimal Transport , 2021 .

[10]  Y. Censor,et al.  An iterative row-action method for interval convex programming , 1981 .

[11]  G. Carlier,et al.  A Numerical Method to Solve Multi-Marginal Optimal Transport Problems with Coulomb Cost , 2016 .

[12]  Jason Altschuler,et al.  Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration , 2017, NIPS.

[13]  Shiguang Shan,et al.  AttGAN: Facial Attribute Editing by Only Changing What You Want , 2017, IEEE Transactions on Image Processing.

[14]  Liang Mi,et al.  Multi-Marginal Optimal Transport Defines a Generalized Metric , 2020, ArXiv.

[15]  Alexander Gasnikov,et al.  Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm , 2018, ICML.

[16]  Gabriel Peyré,et al.  Iterative Bregman Projections for Regularized Transportation Problems , 2014, SIAM J. Sci. Comput..

[17]  Quoc Tran-Dinh,et al.  Generalized self-concordant functions: a recipe for Newton-type methods , 2017, Mathematical Programming.

[18]  Simone Di Marino,et al.  An Optimal Transport Approach for the Schrödinger Bridge Problem and Convergence of Sinkhorn Algorithm , 2019, Journal of Scientific Computing.